dsh-composer-suggest
Manifest validComposer suggestions for DeepSeek Harness: next-message ghost text after a reply and Tab-triggered draft continuation.
dsh-composer-suggest
Composer suggestions for the DeepSeek Harness Web UI.
- Next message: after the agent replies, the empty composer shows the message you are most likely to send next.
- Draft continuation: with text in the composer and the caret at its end, press
Tab. The composer shows "Continuing…" with a spinner while the model works from
the conversation above and your draft; press Tab again to accept the result, or
Esc to cancel. Nothing is asked until you press Tab, and Tab keeps its usual job
anywhere else (empty composer, caret mid-draft, a
/command or@reference). - Tab accepts a suggestion as an editable draft (nothing is sent), Alt+Down / Alt+Up cycle up to three candidates, Esc withdraws the offer, and typing discards it.
- A suggestion longer than what is left of the line wraps in place, at the same column
the accepted text would, and the toolbar row below is pushed down to make room.
To do that the plugin sets a temporary bottom margin on the composer's scroll element
(the one marked
data-input-scroll) and removes it when the suggestion goes away. If a Harness update renames that element, the suggestion still shows but may cover the toolbar until the selector inclient.jsis updated. - Settings → General has one switch per mode, and a status line that shows which model route answered last, how long it took, or why a request failed.
Every suggestion is one model call and uses tokens. It is not written to the Session log and does not show in the token meter.
Install
From a checkout:
git clone https://github.com/WuweiRE/dsh-composer-suggest.git
dsh plugin --profile <name> add ./dsh-composer-suggest
From npm, once a release is published there:
dsh plugin --profile <name> add dsh-composer-suggest
Restart the Harness afterwards, then refresh the Web page. Developed and tested against
DeepSeek Harness 0.2.2-rc.1. It needs a Harness that provides conversation.input.overlay,
settings.general.item, connection.admit(), ctx.llm and session.deriveMessages().
Model
By default a suggestion is answered by the model the Session already uses, at that model's lowest reasoning effort, with no temperature set.
To use another model, type its id (for example claude-sonnet-5-5) in
Settings → General → Model for suggestions and press Enter. Leave it empty to follow
the Session again. It is saved in the browser you typed it in, and the status line under
it reports which route answered last or why a request failed.
To set the model for every browser instead, override the row in your profile's
cordis.patch.yml. Any option you leave out keeps its default, and a model typed in
Settings wins over this:
- id: composer-suggest
name: dsh-composer-suggest
config:
model: claude-sonnet-5-5
Without a provider, the model is looked up among the providers mounted in your
profile, trying the Session's provider first. If none offers it, the request fails with
model-unavailable instead of silently using another model. Set provider and model
together in the configuration to name the route exactly. See cordis.patch.yml for every
option.
Credits and licenses
This plugin is a combination of ideas and code from two MIT-licensed DeepSeek Harness plugins. Their license texts are kept in this repository, and THIRD_PARTY_NOTICES.md lists what comes from where.
| Project | Author | License | Used here |
|---|---|---|---|
| dsh-composer-predictions | Stijnus | MIT, LICENSE.stijnus | Code adapted: the streaming Host endpoint and owner check, prompt construction, candidate normalization, caret measurement, ghost positioning, SSE parsing and the keyboard handling. |
| dsh-composer-prediction | Amir Bazylkhanov | MIT, LICENSE.bazylkhanov | Behaviour reimplemented from its documentation and source: withdrawing a dismissed offer for the rest of the turn, IME handling, reporting a failed request in Settings, and using the model's cheapest advertised reasoning effort. |
What this project adds: continuation is triggered by Tab instead of running on every typing pause, a visible "Continuing…" state with cancel, separate switches for the two modes, a model setting that follows the Session or names a model, a status line in Settings, and short on-screen notices for empty or failed continuations.
This project is released under the MIT License, Copyright (c) 2026 WuweiRE, see LICENSE. It is not affiliated with DeepSeek or with the authors above.
Test
node --test
Comments
Loading…
Similar plugins
by ChuanTianML
Automatic ghost suggestions and one-click next-message drafting for the DeepSeek Harness composer.
★ 4
↓ 337/wk
MIT
JavaScript
Sep 19, 2026
dsh plugin --profile web add dsh-prompt-for-meby dsh-plugin-collection
给 DSH 输入框加上输入预测:回合结束后自动建议你的下一句话,Tab 一键采纳;输入时按会话历史做前缀补全。输入预测 / 自动补全。
★ 8
↓ 459/wk
MIT
JavaScript
Nov 12, 2026
dsh plugin --profile web add dsh-suggest-ghostby QingJ01
Next-prompt ghost text predictions for DeepSeek Harness; Tab or ArrowRight fills an editable draft.
★ 4
↓ 1.2k/wk
MIT
JavaScript
Nov 5, 2026
dsh plugin --profile web add dsh-prompt-predictionby Tleon-H
After each reply, shows a gray next-prompt suggestion in the empty composer that Tab or → accepts, and ↑ in an empty composer recalls your last sent message; nothing is sent automatically.
★ 0
MIT
JavaScript
Oct 28, 2026
dsh plugin --profile web add dsh-next-promptby littepointR
Ghost-text next-prompt prediction in the DeepSeek Harness Web composer, accepted with Tab.
★ 0
MIT
JavaScript
Oct 27, 2026
dsh plugin --profile web add @local/dsh-prompt-forecastComposer prompt enhancement for DSH Web: a ✨ button rewrites the current draft in place after asking only about genuine ambiguity, and an empty composer shows a grey next-message ghost that Tab or a c
★ 0
MIT
TypeScript
dsh plugin --profile web add dsh-composer-enhance